Ab Initio Machine Learning in Chemical Compound Space

Author(s)
Bing Huang, O. Anatole von Lilienfeld
Abstract

Chemical compound space (CCS), the set of all theoretically conceivable combinations of chemical elements and (meta-)stable geometries that make up matter, is colossal. The first-principles based virtual sampling of this space, for example, in search of novel molecules or materials which exhibit desirable properties, is therefore prohibitive for all but the smallest subsets and simplest properties. We review studies aimed at tackling this challenge using modern machine learning techniques based on (i) synthetic data, typically generated using quantum mechanics based methods, and (ii) model architectures inspired by quantum mechanics. Such Quantum mechanics based Machine Learning (QML) approaches combine the numerical efficiency of statistical surrogate models with an ab initio view on matter. They rigorously reflect the underlying physics in order to reach universality and transferability across CCS. While state-of-the-art approximations to quantum problems impose severe computational bottlenecks, recent QML based developments indicate the possibility of substantial acceleration without sacrificing the predictive power of quantum mechanics.

Organisation(s)
Computational Materials Physics
External organisation(s)
Universität Basel
Journal
Chemical Reviews
Volume
121
Pages
10001-10036
No. of pages
36
ISSN
0009-2665
DOI
https://doi.org/10.1021/acs.chemrev.0c01303
Publication date
08-2021
Peer reviewed
Yes
Austrian Fields of Science 2012
103025 Quantum mechanics, 102019 Machine learning, 104017 Physical chemistry
Keywords
Portal url
https://ucris.univie.ac.at/portal/en/publications/ab-initio-machine-learning-in-chemical-compound-space(d537baf9-effe-4f31-a23c-3c6fc2cc1a41).html